canary
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for web application regression monitoring. It leverages standard browser automation tools (Playwright) to visit user-specified URLs and collect metrics.
- [DATA_EXPOSURE]: While the skill navigates to external URLs and captures screenshots/logs, this is the core functionality requested by the user. The skill does not access sensitive local files or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites (console logs, status codes). While this constitutes an attack surface, the risk is mitigated by the 'disable-model-invocation' configuration, which prevents the model from processing potentially malicious instructions found on those pages during the execution loop.
Audit Metadata